Sotabase

Career

· Researcher, Latent Logic2019–2019
· Researcher, Waymo2019–
· DPhil Computer Science, Artificial Intelligence, University of Oxford2016–2019
· Master of Science (MSc), Computational Statistics and Machine Learning, UCL2014–2015
· AVP, Capital Management, Barclays Capital2012–2014
· Advisor, Banking Risk, KPMG UK2010–2012
· Credit Risk, ICICI Bank2008–2010
· MBA, Finance and Economics, XLRI Jamshedpur2006–2008

Publications (10)

Learning From Demonstration in the Wild
IEEE International Conference on Robotics and Automation · 2018
78
cited
Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving
IEEE/RJS International Conference on Intelligent RObots and Systems · 2022
69
cited
Fast Efficient Hyperparameter Tuning for Policy Gradients
Neural Information Processing Systems · 2019
33
cited
Alternating Optimisation and Quadrature for Robust Control
AAAI Conference on Artificial Intelligence · 2016
23
cited
Embedding Synthetic Off-Policy Experience for Autonomous Driving via Zero-Shot Curricula
Conference on Robot Learning · 2022
19
cited
Fingerprint Policy Optimisation for Robust Reinforcement Learning
International Conference on Machine Learning · 2018
18
cited
Alternating Optimisation and Quadrature for Robust Reinforcement Learning
arXiv.org · 2016
6
cited
Contextual Policy Optimisation
arXiv.org · 2018
3
cited
Robust Reinforcement Learning with Bayesian Optimisation and Quadrature
Journal of machine learning research · 2020
1
cited
Rate-Informed Discovery via Bayesian Adaptive Multifidelity Sampling
Conference on Robot Learning · 2024
Sotabase
Supratik Paul | Researcher Profile | Sotabase | Sotabase